Container door anomaly detection method, system and equipment and storage medium
By installing a camera on the spreader to collect container images, detect keyholes and locks, and judge the abnormal status of the box door, the problem of abnormal opening of the box door during container transportation is solved, and safety and stability are improved.
Patent Information
- Application Number
- CN202510332462.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-20
- Publication Date
- 2025-07-04
AI Technical Summary
During container transportation, abnormal opening of the box door causes the goods to fall out, which poses safety risks. The existing technology lacks effective detection methods.
By installing a camera on the spreader to acquire container images taken from the top, use the target detection model to detect the keyhole and the lock head, count the number of lock heads in the lock head position area, and judge whether the box door is opened abnormally based on preset conditions.
It realizes abnormal detection of container doors before lifting, avoids cargo falling out, improves the safety and stability of the transportation process, and the detection method is simple and easy to deploy and can achieve fast and accurate real-time detection.
Smart Images
Figure CN120252801A_ABST
Abstract
Description
Background Art
[0002] During the transportation of containers, for various reasons, the container door may be abnormally opened, resulting in the dumping and spilling of goods. If the container door is abnormally opened during high-altitude hoisting, the falling goods are also likely to hit the staff and vehicles, causing casualties and property losses. Therefore, during the hoisting process, there is an urgent need to detect whether the container door is abnormally opened.
[0003] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present application. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention
[0004] Aiming at the problems in the prior art, the purpose of the present application is to provide a method, system, device and storage medium for detecting abnormal opening of a container door, which realizes the abnormal detection of the container door before hoisting, avoids the goods in the container from falling out due to the abnormal opening of the container door during hoisting, and improves the safety and stability during the container transportation process. The implementation method of this method is simple, easy to deploy, and can achieve fast, accurate and real-time detection.
[0005] The embodiment of the present application provides a method for detecting abnormal opening of a container door, including the following steps:
[0006] Collect a top-down container image captured by a camera arranged on the spreader;
[0007] Detect the keyhole and the lock head in the container image;
[0008] Determine the lock head position area in the container image according to the detected keyhole;
[0009] Count the number of lock heads in the lock head position area;
[0010] Judge whether the container door is abnormally opened according to the number and position of the lock heads and the preset abnormal conditions of the container door.
[0011] In some embodiments, before determining the lock head position area in the container image according to the detected keyhole, the following steps are further included:
[0012] Judge whether the number of keyholes in the container image is greater than 0 and less than or equal to the preset maximum number of keyholes;
[0013] If not, do not process the container image.
[0014] In some embodiments, determining the lock head position area in the container image according to the detected keyhole includes the following steps:
[0015] Set the upward direction of the image in the container as the positive direction of the y-axis;
[0016] Determine whether the number of keyholes in the container image is equal to the preset maximum number of keyholes;
[0017] If so, take the two keyholes with the smallest y coordinate values in the container image as the keyholes of the target container;
[0018] Determine the position area of the lock head in the container image according to the keyholes of the target container.
[0019] In some embodiments, after determining whether the number of keyholes in the container image is equal to the preset maximum number of keyholes, the following steps are further included:
[0020] If the number of keyholes in the container image is less than the preset maximum number of keyholes and greater than 0, cluster the keyholes to obtain two cluster centers;
[0021] Select the keyhole corresponding to the cluster center with a smaller y coordinate value as the keyhole of the target container;
[0022] Determine the position area of the lock head in the container image according to the keyholes of the target container.
[0023] In some embodiments, determining the position area of the lock head in the container image according to the keyholes of the target container includes the following steps:
[0024] Set the rightward direction of the image in the container as the positive direction of the x-axis;
[0025] Determine the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the positions of the keyholes of the target container in the container image, and determine the position of the rectangular frame corresponding to the lock head position area.
[0026] In some embodiments, determining the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the positions of the keyholes of the target container in the container image includes the following steps:
[0027] Determine whether there are two keyholes of the target container;
[0028] If there are two keyholes of the target container, determine the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the two keyholes;
[0029] If there is only one keyhole of the target container, determine the y-axis coordinate range and one side boundary point of the x-axis of the lock head position area, and extend the other side boundary point of the x-axis of the lock head position area to one side boundary of the container image.
[0030] In some embodiments, the abnormal conditions of the container door include: setting the upward direction of the image in the container image as the positive direction of the y-axis, the number of lock heads in the lock head position area is less than the preset maximum number of lock heads, and the difference between the maximum value and the minimum value of the y-axis coordinates of all lock heads is greater than the preset difference threshold.
[0031] In some embodiments, according to the number and position of the lock heads and the preset abnormal conditions of the container door, determining whether the container door is abnormally opened includes the following steps:
[0032] Determine whether a lock head is located within the lock head position area;
[0033] If no lock head is located within the lock head position area, then determine whether there is a lock head in the non-lock head position area in the container image;
[0034] If no lock head is located in the non-lock head position area in the container image, it is determined that only the front container door is included in the container image, and the current process ends;
[0035] If a lock head is located in the non-lock head position area in the container image, calculate the difference between the maximum value and the minimum value of the y-axis coordinates of the located lock heads. If the difference is greater than the first difference threshold, it is determined that the container door in the container image is abnormally opened. If the difference is less than or equal to the first difference threshold, it is determined that the container door in the container image is not opened.
[0036] In some embodiments, after determining whether a lock head is located within the lock head position area, the following steps are further included:
[0037] If a lock head is located within the lock head position area, determine whether the number of lock heads is equal to the preset maximum number of lock heads;
[0038] If the number of lock heads is equal to the preset maximum number of lock heads, it is determined that the container door in the container image is not opened;
[0039] If the number of lock heads is less than the preset maximum number of lock heads, calculate the difference between the maximum value and the minimum value of the y-axis coordinates of the located lock heads. If the difference is greater than the second difference threshold, it is determined that the container door in the container image is abnormally opened. If the difference is less than or equal to the second difference threshold, it is determined that the container door in the container image is not opened.
[0040] In some embodiments, a trained object detection model is used to detect lock holes and lock heads in the container image.
[0041] In some embodiments, collecting a top-down container image from a camera provided on the spreader includes the following steps:
[0042] When the spreader descends, the height of the spreader is detected, and when the spreader descends to a preset height, a top-down view image of the container is collected from a camera provided on the spreader.
[0043] An embodiment of the present application further provides a container door abnormal detection system for implementing the container door abnormal detection method. The system includes:
[0044] An image acquisition module configured to acquire a top-down view image of the container from a camera provided on the spreader;
[0045] A target detection module configured to detect a keyhole and a lock head in the container image;
[0046] A lock head positioning module configured to determine the lock head position area in the container image according to the detected keyhole and count the number of lock heads in the lock head position area;
[0047] An abnormal judgment module for judging whether the container door is abnormally opened according to the number and position of the lock heads and the preset container door abnormal conditions.
[0048] An embodiment of the present application further provides a container door abnormal detection device, including:
[0049] A processor;
[0050] A memory storing executable instructions of the processor;
[0051] Wherein, the processor is configured to execute the steps of the above-mentioned container door abnormal detection method by executing the executable instructions.
[0052] An embodiment of the present application further provides a computer-readable storage medium for storing a program, and when the program is executed by a processor, the steps of the container door abnormal detection method are implemented.
[0053] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present disclosure.
[0054] The container door abnormal detection method, system, device and storage medium of the present application have the following
[0055] Beneficial effects:
[0056] By adopting the container door abnormal detection method of the present application, in the container image obtained by top-down shooting, first determine the area of the possible position of the lock head in the container image, then count the number of lock heads in the area of the lock head position, and judge whether the container door is abnormally opened according to the number of lock heads in the area of the lock head position, so as to realize the abnormal detection of the container door before hoisting, avoid the goods in the container falling out due to the abnormal opening of the container door during the hoisting process, and improve the safety and stability during the container transportation process. The implementation method of this method is simple, easy to deploy, and can realize fast and accurate real-time detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] Other features, objects, and advantages of the present application will become more apparent by reading the detailed description of the non-limiting embodiments with reference to the following drawings.
[0058] Figure 1 is a flowchart of the container door abnormal detection method according to an embodiment of the present application;
[0059] Figure 2 is a schematic diagram of a container image according to an embodiment of the present application;
[0060] Figure 3 is a schematic diagram of detecting a keyhole and a lock head in a container image according to an embodiment of the present application;
[0061] Figure 4 is a schematic diagram of the structure of a container door abnormal detection system according to an embodiment of the present application;
[0062] Figure 5 is a schematic diagram of the structure of a container door abnormal detection device according to an embodiment of the present application;
[0063] Figure 6 is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0064] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more complete and comprehensive, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.
[0065] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices. Although terms such as "first" or "second" are used in this specification to denote certain features, they are only for the purpose of indication and do not limit the quantity and importance of the specific features.
[0066] The flowcharts shown in the accompanying drawings are only exemplary illustrations and do not necessarily include all steps. For example, some steps can be further decomposed, while some steps can be combined or partially combined. Therefore, the actual execution order may be changed according to the actual situation.
[0067] In the prior art, there is a lack of an effective detection method for whether the container door is abnormally opened. During the container transportation process, if the container door is opened abnormally, the goods inside will fall out, spill, etc. To solve this problem, an embodiment of the present application provides a method for detecting abnormal opening of a container door, aiming to perform an abnormal opening detection before lifting the container door by a spreader, so as to avoid the goods falling out and injuring the staff or vehicles during the lifting process.
[0068] As Figure 1 shown, an embodiment of the present application provides a method for detecting abnormal opening of a container door, including the following steps:
[0069] S100: Acquire a top-down view container image captured by a camera disposed on the spreader;
[0070] In this embodiment, step S100 specifically includes the following steps:
[0071] When the spreader descends, detect the height of the spreader, and when the spreader descends to a preset height, acquire a top-down view container image captured by a camera disposed on the spreader; for example, obtain the descending height of the spreader in real time through a PLC (Programmable Logic Controller), and when the spreader descends to the preset height, trigger the camera disposed on the spreader to capture an image; when the camera captures the image, the viewing angle is vertically downward and is aligned with the front and rear container doors;
[0072] Because when the spreader has not descended or is still at a relatively high position during the descent, there may be a relatively large number of containers in the photos taken by the spreader, and the area of each container in the image is very small, resulting in inaccurate detection. Therefore, it is necessary to collect images when the spreader descends to a preset height. The preset height can be set according to the actual scenario and requirements, so that the number of containers included in the image taken by the camera on the spreader does not exceed two at a time;
[0073] The number of cameras installed on the spreader can be selected according to needs. For example, one or more cameras can be installed on the spreader. When multiple cameras are installed on the spreader, the container images taken by each camera are respectively processed using the container door abnormal detection method of the present application;
[0074] S200: Detect the lock holes and lock heads in the container image;
[0075] In this embodiment, a trained object detection model is used to detect the lock holes and lock heads in the container image; the object detection model can be an object detection model constructed based on a neural network, and is trained using multiple sample images marked with the positions of the lock holes and lock heads. After training until the model converges, a trained object detection model is obtained;
[0076] Figure 2 is a schematic diagram of a container image according to an embodiment of the present application; taking Figure 2 as an example, there are two containers A1 and A2 in the container image, where container A1 is the target container. There are a total of four lock holes K1, K2, K3, and K4 in this container image. Among them, lock holes K1 and K2 are the lock holes of the target container, and lock holes K3 and K4 are the lock holes of non-target containers; when performing lock hole target detection in the container image, the positions where the four lock holes K1, K2, K3, and K4 are located can be detected; Figure 2 The number and positions of the lock holes shown in are only examples. In actual applications, with the differences in factors such as the position, size of the container, and the position of the spreader camera, the positions and numbers of the lock holes in the obtained container image will also change accordingly;
[0077] S300: Determine the lock head position area in the container image according to the detected lock holes;
[0078] Figure 3 is a schematic diagram of detecting lock holes and lock heads in a container image according to an embodiment of the present application; taking Figure 3 as an example, the lock holes K1 and K2 of the target container A1 are selected from the four detected lock holes K1, K2, K3, and K4, and the lock head position area M is determined according to the lock holes K1 and K2. The lock head position area is a rectangular frame;
[0079] S400: Count the number of lock heads in the lock head position area;
[0080] Taking Figure 3 as an example, if the lock heads T1, T2, T3, and T4 are located in the lock head position area, then the number of lock heads in the lock head position area is four; Figure 3 The number and positions of the lock heads shown are only examples. In actual applications, the positions and numbers of the lock heads in the container image obtained will vary with factors such as the position of the container, its size, and the position of the spreader camera;
[0081] S500: Determine whether the container door is abnormally opened according to the number and positions of the lock heads and the preset abnormal conditions of the container door;
[0082] In this embodiment, after determining that the container door is abnormally opened, the current lifting process can be interrupted through program control to avoid lifting a container with an opened door, and an alarm message can be sent to the staff to timely remind the staff to perform abnormal handling.
[0083] Among them, the abnormal conditions of the container door are that the number and positions of the lock heads do not meet the requirements of the number and positions that should be detected when the container door is closed.
[0084] Optionally, in one implementation, taking the lower left corner of the container image as the zero point, the upward direction as the positive y-axis direction, and the rightward direction as the positive x-axis direction, the abnormal conditions of the container door include that the number of lock heads in the lock head position area is less than the preset maximum number of lock heads, and the difference between the maximum y-axis coordinate and the minimum y-axis coordinate of all lock heads is greater than the preset difference threshold. Among them, when calculating the y-axis coordinate difference of all lock heads, all lock heads can include the lock heads within the lock head position area or the lock heads detected outside the lock head position area.
[0085] By adopting the container door abnormal detection method of the present application, in the container image taken from above obtained through step S100, first determine the lock head position area where the lock heads may exist in the container image through steps S200 and S300, then count the number of lock heads in the lock head position area through step S400, and determine whether the container door is abnormally opened according to the number of lock heads in the lock head position area through step S500, thereby realizing abnormal detection of the container door before lifting, avoiding the goods in the container from falling out due to the abnormal opening of the container door during the lifting process, and improving the safety and stability during the container transportation process. The implementation method of this method is simple, easy to deploy, and can achieve fast, accurate, and real-time detection.
[0086] In this embodiment, before the step S300: Determine the lock head position area in the container image according to the detected lock holes, the following steps are further included:
[0087] Determine whether the number of keyholes in the container image is greater than 0 and less than or equal to a preset maximum number of keyholes; here, the preset maximum number of keyholes is equal to twice the number of keyholes of a container door.
[0088] If not, do not process the container image.
[0089] If the number of keyholes in the container image is 0, it means there is no container in the captured container image, so do not process the container image and end the current process. If the number of keyholes in the container image is greater than the preset maximum number of keyholes, it means the captured container image includes more than 2 containers. At this time, the spreader is too high and the field of view is too large, and subsequent detections will not be accurate enough. Therefore, do not process the container image either, end the current process, lower the spreader by a certain height, and then re - execute the process of the container door abnormality detection method.
[0090] In this embodiment, the step S300: Determine the lock head position area in the container image according to the detected keyholes, includes the following steps:
[0091] Set the upward direction of the image in the container image as the positive y - axis direction.
[0092] Determine whether the number of keyholes in the container image is equal to the preset maximum number of keyholes.
[0093] If so, take the two keyholes with the smallest y - coordinate values in the container image as the keyholes of the target container; Figure 3 For example, each container door has 2 keyholes, so the preset maximum number of keyholes is 4. Since 2 container doors are captured in the image, 4 keyholes are detected. Take the two keyholes K1 and K2 at the lower position as the keyholes of the target container.
[0094] Determine the lock head position area in the container image according to the keyholes of the target container. By determining the lock head position area, the influence of the lock heads of non - target containers above can be excluded.
[0095] In this embodiment, after determining whether the number of keyholes in the container image is equal to the preset maximum number of keyholes, the following steps are further included:
[0096] If the number of keyholes in the container image is less than the preset maximum number of keyholes and greater than 0, cluster the keyholes to obtain two cluster centers. For example, if the preset maximum number of keyholes is 4, when the number of keyholes detected in the container image is 1 to 3, after summarizing the y-axis coordinates of the keyholes, perform kmeans clustering (k-means clustering algorithm) on the y-axis coordinates of all keyholes to obtain two cluster centers, that is, divide the y-axis coordinates of all keyholes into two categories, and take the category with the smaller cluster center as the keyholes of the target container. Kmeans clustering is an iterative clustering analysis algorithm. Its steps are to pre-divide the data into k groups, then randomly select k objects as the initial cluster centers, and then calculate the distance between each object and each seed cluster center, and assign each object to the cluster center closest to it.
[0097] Select the keyhole corresponding to the cluster center with the smaller y coordinate value as the keyhole of the target container.
[0098] Determine the position area of the lock head in the container image according to the keyholes of the target container.
[0099] In this embodiment, determining the position area of the lock head in the container image according to the keyholes of the target container includes the following steps:
[0100] Take the right direction of the image in the container image as the positive x-axis direction;
[0101] Determine the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the position of the keyholes of the target container in the container image, and determine the position of the rectangular frame corresponding to the lock head position area. The lock head position area is a rectangular frame, and its coordinate range is (x_left, y_max, x_right, y_min).
[0102] Among them, determining the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the position of the keyholes of the target container in the container image includes the following steps:
[0103] Judge whether the number of keyholes of the target container is two;
[0104] If there are two keyholes of the target container, determine the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the two keyholes; taking Figure 3 as an example, in the coordinate range (x_left, y_max, x_right, y_min) of the lock head position area M, x_left is the x-axis coordinate of the leftmost point of the left keyhole of the target container. x_right is the x-axis coordinate of the rightmost point of the right keyhole of the target container. y_max and y_min are respectively the maximum y-axis coordinate and the minimum y-axis coordinate of the keyholes of the target container.
[0105] If there is only one keyhole of the target container, determine the y-axis coordinate range and one side boundary point of the x-axis of the key head position area according to this keyhole, and extend the other side boundary point of the x-axis of the key head position area to one side boundary of the container image. For example, if only the keyhole on the right side of the target container is detected, determine y_max and y_min according to the maximum and minimum values of the y-axis of this keyhole, determine x_right according to the coordinates of the right boundary point of this keyhole, and set x_left to 0. Or, if only the keyhole on the left side of the target container is detected, determine y_max and y_min according to the maximum and minimum values of the y-axis of this keyhole, determine x_left according to the coordinates of the left boundary point of this keyhole, and set x_right to the maximum width value w of the container image.
[0106] In this embodiment, the step S500: judging whether the container door is abnormally opened according to the number and position of the key heads and the preset abnormal conditions of the container door includes the following steps:
[0107] Judge whether a key head is located within the key head position area;
[0108] If no key head is located within the key head position area, judge whether there is a key head in the non-key head position area of the container image;
[0109] If no key head is located in the non-key head position area of the container image, it is determined that only the front container door is included in the container image, and the current process ends;
[0110] If a key head is located in the non-key head position area of the container image, calculate the difference between the maximum and minimum values of the y-axis coordinates of the detected key heads. If the difference is greater than the first difference threshold, it is determined that the container door in the container image is abnormally opened. If the difference is less than or equal to the first difference threshold, it is determined that the container door in the container image is not opened. The specific value of the first difference threshold here can be set according to specific needs. For example, considering factors such as the height of the spreader shooting, the resolution of the camera, and the size of the container, a reasonable first difference threshold is selected so that when the container door is abnormally opened, the difference between the maximum y-axis coordinate and the minimum y-axis coordinate of the key head is greater than the first difference threshold.
[0111] Since there may be two containers in the container image, if no lock is located within the lock position area, it is possible that the door of the lower container is the front door and the door of the upper container is the back door, and multiple locks can be located outside the lock position area. However, there is still a situation where the door of the lower container is abnormally opened, causing the lock to move outside the lock position area. Therefore, it is necessary to judge the difference in the y-axis coordinates. If the difference in the y-axis coordinates is relatively small, it is considered that the lock is for the door of the upper container. If the difference in the y-axis coordinates is relatively large, it is considered that the door of the lower container is the back door and the door of the lower container is opened. In this scenario, since the opening degree of the door of the lower container is relatively large, there is only one lower container in the container image (according to the program setting, when there is only one upper container, the spreader will not lower, and the process of the abnormal detection method for the container door will not be started).
[0112] In this embodiment, after judging whether a lock is located within the lock position area, the following steps are further included:
[0113] If a lock is located within the lock position area, judge whether the number of locks is equal to the preset maximum number of locks; here, the preset maximum number of locks is the number of locks on the back door of a container. For Figure 3 example, a container back door has 4 locks, so the preset maximum number of locks is set to 4;
[0114] If the number of locks is equal to the preset maximum number of locks, it is determined that the container door in the container image is not opened; for Figure 3 example, when 4 locks are located within the lock position area M, it indicates that the container door is not opened at this time, and the relationship state is maintained;
[0115] If the number of locks is less than the preset maximum number of locks, calculate the difference between the maximum and minimum y-axis coordinates of the located locks. If the difference is greater than the second difference threshold, it is determined that the container door in the container image is abnormally opened. If the difference is less than or equal to the second difference threshold, it is determined that the container door in the container image is not opened. For example, when the number of locks is 1 to 3, considering that there may be detection errors in the target detection model, it is still necessary to judge whether the container door is abnormally opened according to the difference in the y-axis coordinates of the located locks. If the difference is greater than the second difference threshold, it means that the door forms a certain angle with the x-axis, and at this time, the difference in the y-axis coordinates of the locks is relatively large. The specific value of the second difference threshold can be set according to specific needs. For example, considering factors such as the height at which the spreader takes pictures, the resolution of the camera, and the size of the container, a reasonable first difference threshold is selected so that when the container door is abnormally opened, the difference between the maximum and minimum y-axis coordinates of the locks is greater than the second difference threshold. The values of the second difference threshold and the first difference threshold can be the same or set to two different thresholds.
[0116] As shown Figure 4 in the following figure, an embodiment of the present application further provides a container door abnormal detection system for implementing the above-mentioned container door abnormal detection method. The system includes:
[0117] An image acquisition module M100, configured to acquire a top-down view container image captured by a camera disposed on a spreader;
[0118] A target detection module M200, configured to detect a keyhole and a lock head in the container image;
[0119] A lock head positioning module M300, configured to determine a lock head position area in the container image according to the detected keyhole, and count the number of lock heads in the lock head position area;
[0120] An abnormality determination module M400, configured to determine whether the container door is abnormally opened according to the number and position of the lock heads and a preset container door abnormality condition.
[0121] By adopting the container door abnormal detection system of the present application, in the top-down view container image obtained by the image acquisition module M100, first, the lock head position area where the lock head may exist in the container image is determined by the keyhole detection module M200 and the lock head detection module M300, then the number of lock heads is counted in the lock head position area by the lock head positioning module M300, and the abnormality determination module M400 determines whether the container door is abnormally opened according to the number of lock heads in the lock head position area, thereby realizing the abnormal detection of the container door before hoisting, avoiding the goods in the container from falling out due to the abnormal opening of the container door during the hoisting process, and improving the safety and stability during the container transportation process. The implementation method is simple, easy to deploy, and can achieve fast, accurate and real-time detection.
[0122] In the container door abnormal detection system of the present application, the functions of each module can be implemented by the specific implementation manners of the above-mentioned container door abnormal detection method, which will not be elaborated here.
[0123] An embodiment of the present application further provides a container door abnormal detection device, including a processor; a memory, in which executable instructions of the processor are stored; wherein, the processor is configured to execute the steps of the above-mentioned container door abnormal detection method by executing the executable instructions.
[0124] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, method, or program product. Therefore, various aspects of the present application can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as "circuitry", "module", or "platform".
[0125] Reference is now made to Figure 5 to describe the electronic device 600 according to this embodiment of the present application. Figure 5 The electronic device 600 shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.
[0126] As Figure 5 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.
[0127] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present application described in the above-mentioned container door abnormal detection method part of this specification. For example, the processing unit 610 can execute the steps as Figure 1 shown in
[0128] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.
[0129] The storage unit 620 may also include a program / utilities 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.
[0130] The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.
[0131] The electronic device 600 can also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device (such as a router, a modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. Such communication can be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 through the bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.
[0132] In the container door abnormal detection device, when the program in the memory is executed by the processor, the steps of the above-mentioned container door abnormal detection method are implemented. Therefore, the device can also obtain the technical effects of the above-mentioned container door abnormal detection method.
[0133] The embodiment of the present application also provides a computer-readable storage medium for storing a program, and when the program is executed by the processor, the steps of the above-mentioned container door abnormal detection method are implemented. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code. When the program product is executed on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments described in the above-mentioned container door abnormal detection method part of this specification.
[0134] Reference Figure 6 As shown, a program product 800 for implementing the above method according to an embodiment of the present application is described. It can be a portable compact disc read-only memory (CD-ROM) and includes program code, and can be executed on a terminal device, such as a personal computer. However, the program product of the present application is not limited to this. In this document, a readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.
[0135] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0136] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0137] The program code for performing the operations of this application may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user computing device, partially on the user device, execute as a stand-alone software package, execute partially on the user computing device and partially on a remote computing device, or execute entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).
[0138] When the program in the computer storage medium is executed by a processor, the steps of the container door abnormality detection method are implemented. Therefore, the computer storage medium can also achieve the technical effects of the above container door abnormality detection method.
[0139] The above content is a further detailed description of the present application in combination with specific preferred embodiments. It cannot be determined that the specific implementation of the present application is only limited to these descriptions. For those of ordinary skill in the technical field to which the present application pertains, without departing from the concept of the present application, several simple deductions or substitutions can still be made, and all should be regarded as falling within the protection scope of the present application.
Claims
1. A method for detecting abnormal conditions of a container door, characterized in that, The method includes the following steps: Collect a top-down view image of the container captured by a camera installed on the spreader; Detect the lock holes and lock heads in the container image; Determine the lock head position area in the container image according to the detected lock holes; Count the number of lock heads in the lock head position area; Judge whether the container door is abnormally opened according to the number and position of the lock heads and the preset abnormal conditions of the container door.
2. The container door abnormal detection method according to claim 1, wherein Before determining the lock head position area in the container image according to the detected lock holes, the following steps are further included: Judge whether the number of lock holes in the container image is greater than 0 and less than or equal to the preset maximum number of lock holes; If not, do not process the container image.
3. The container door abnormal detection method according to claim 1, characterized in that, Determining the lock head position area in the container image according to the detected lock holes includes the following steps: Set the upward direction of the image in the container image as the positive direction of the y-axis; Judge whether the number of lock holes in the container image is equal to the preset maximum number of lock holes; If so, take the two lock holes with the smallest y coordinate values in the container image as the lock holes of the target container; Determine the lock head position area in the container image according to the lock holes of the target container.
4. The container door abnormal detection method according to claim 3, characterized in that, After judging whether the number of lock holes in the container image is equal to the preset maximum number of lock holes, the following steps are further included: If the number of lock holes in the container image is less than the preset maximum number of lock holes and greater than 0, cluster the lock holes to obtain two cluster centers; Select the lock hole corresponding to the cluster center with the smaller y coordinate value as the lock hole of the target container; Determine the lock head position area in the container image according to the lock holes of the target container.
5. The container door abnormal detection method according to claim 3 or 4, characterized in that Determining the lock head position area in the container image according to the lock holes of the target container includes the following steps: Set the rightward direction of the image in the container image as the positive direction of the x-axis; Determine the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the positions of the lock holes of the target container in the container image, and determine the position of the rectangular frame corresponding to the lock head position area.
6. The container door abnormal detection method according to claim 5, characterized in that Determining the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the positions of the lock holes of the target container in the container image includes the following steps: Judge whether there are two lock holes of the target container; If there are two lock holes of the target container, determine the x-axis coordinate range and y-axis coordinate range of the lock head position area according to the two lock holes; If there is only one lock hole of the target container, determine the y-axis coordinate range and one side boundary point of the x-axis of the lock head position area, and extend the other side boundary point of the x-axis of the lock head position area to one side boundary of the container image.
7. The container door abnormal detection method according to claim 1, characterized in that The abnormal conditions of the container door include: setting the upward direction of the image in the container image as the positive direction of the y-axis, the number of lock heads in the lock head position area is less than the preset maximum number of lock heads, and the difference between the maximum y-axis coordinate value and the minimum y-axis coordinate value of all lock heads is greater than the preset difference threshold.
8. The container door abnormal detection method according to claim 1, wherein, Judging whether the container door is abnormally opened according to the number and position of the lock heads and the preset abnormal conditions of the container door includes the following steps: Determine whether a lock head is located within the lock head position area; If no lock head is located within the lock head position area, then determine whether there is a lock head within the non-lock head position area in the container image; If no lock head is located within the non-lock head position area in the container image, then determine that the container image only contains the front door of the container, and end the current process; If a lock head is located within the non-lock head position area in the container image, calculate the difference between the maximum and minimum y-axis coordinates of the located lock head. If the difference is greater than the first difference threshold, then determine that the container door in the container image is abnormally opened. If the difference is less than or equal to the first difference threshold, then determine that the container door in the container image is not opened.
9. The container door abnormal detection method according to claim 8, characterized in that, After determining whether a lock head is located within the lock head position area, the following steps are further included: If a lock head is located within the lock head position area, determine whether the number of lock heads is equal to the preset maximum number of lock heads; If the number of lock heads is equal to the preset maximum number of lock heads, then determine that the container door in the container image is not opened; If the number of lock heads is less than the preset maximum number of lock heads, calculate the difference between the maximum and minimum y-axis coordinates of the located lock head. If the difference is greater than the second difference threshold, then determine that the container door in the container image is abnormally opened. If the difference is less than or equal to the second difference threshold, then determine that the container door in the container image is not opened.
10. The container door abnormal detection method according to claim 1, wherein Use the trained object detection model to detect the lock hole and the lock head in the container image.
11. The container door abnormal detection method according to claim 1, characterized in that, The step of collecting a top-down view of the container image from the camera provided on the spreader includes the following steps: When the spreader descends, detect the height of the spreader, and when the spreader descends to a preset height, collect a top-down view of the container image from the camera provided on the spreader.
12. A container door abnormal detection system, characterized in that, For implementing the container door abnormal detection method according to any one of claims 1 to 11, the system includes: An image acquisition module configured to collect a top-down view of the container image from the camera provided on the spreader; An object detection module configured to detect the lock hole and the lock head in the container image; A lock head positioning module configured to determine the lock head position area in the container image according to the detected lock hole and count the number of lock heads in the lock head position area; An abnormal judgment module for judging whether the container door is abnormally opened according to the number and position of the lock heads and the preset door abnormal conditions.
13. An abnormal detection device for the container door, characterized in that, Includes: A processor; A memory in which executable instructions of the processor are stored; Wherein, the processor is configured to execute the steps of the container door abnormal detection method according to any one of claims 1 to 11 by executing the executable instructions.
14. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the container door abnormal detection method according to any one of claims 1 to 11.